Acoustic signal processing adaptive to user-to-microphone distances

Abstract

Apparatus, systems, methods, and articles of manufacture are disclosed for acoustic signal processing adaptive to microphone distances. An example system includes a microphone to convert an acoustic signal to an electrical signal and one or more processors to: estimate a distance between a source of the acoustic signal and the microphone; select a signal processing mode based on the distance; and process the electrical signal in accordance with the selected processing mode.

1 . (canceled) 
     
     
         2 . An apparatus comprising:
 interface circuitry;   instructions; and   processor circuitry to be programmed by the instructions to:
 estimate a distance between a source of an acoustic signal and a microphone that detected the acoustic signal, the estimate based on reverberation; 
 select a signal processing mode based on the distance; and 
 process an electrical signal representative of the acoustic signal in accordance with the selected signal processing mode. 
   
     
     
         3 . The apparatus of  claim 2 , wherein the processor circuitry is to:
 identify a decibel-based metric based on the reverberation;   perform a comparison of the decibel-based metric to a threshold; and   categorize the distance as near-field or far-field based on the comparison.   
     
     
         4 . The apparatus of  claim 3 , wherein the processor circuitry is to execute an artificial intelligence model to identify the decibel-based metric. 
     
     
         5 . The apparatus of  claim 4 , wherein the processor circuitry is to implement a training phase in which the decibel-based metric is identified based on a direct pulse of the acoustic signal. 
     
     
         6 . The apparatus of  claim 3 , wherein the processor circuitry is to dereverberate the electrical signal when the distance is far-field. 
     
     
         7 . The apparatus of  claim 2 , wherein the processor circuitry is to estimate the distance for subsequent frames of the electrical signal. 
     
     
         8 . The apparatus of  claim 2 , wherein the distance is a first distance, the source is a first source, the acoustic signal is a first acoustic signal, the signal processing mode is a first signal processing mode, and the electrical signal is a first electric signal, the processor circuitry to:
 estimate a second distance between a second source of a second acoustic signal and the microphone that detected the second acoustic signal;   select a second signal processing mode based on the second distance; and   process a second electrical signal representative of the second acoustic signal in accordance with the selected second signal processing mode.   
     
     
         9 . An apparatus comprising:
 means for converting an acoustic signal to an electrical signal; and   means for processing signals, the processing means to:   estimate a distance between a source of an acoustic signal and a microphone that detected the acoustic signal, the estimate based on reverberation;   select a signal processing mode based on the distance; and   process an electrical signal representative of the acoustic signal in accordance with the selected signal processing mode.   
     
     
         10 . The apparatus of  claim 9 , wherein the processing means is to:
 identify a decibel-based metric using the reverberation;   perform a comparison of the decibel-based metric to a threshold; and   categorize the distance as foreground or background based on the comparison.   
     
     
         11 . The apparatus of  claim 10 , wherein the processing means is to apply a machine learning model to identify the decibel-based metric. 
     
     
         12 . The apparatus of  claim 11 , wherein the processing means is to implement a training phase in which the decibel-based metric is identified based on a direct pulse of the acoustic signal. 
     
     
         13 . The apparatus of  claim 10 , wherein the processing means is to dereverberate the electrical signal when the distance is background. 
     
     
         14 . The apparatus of  claim 9 , wherein the processing means is to dynamically estimate the distance across frames of the electrical signal. 
     
     
         15 . The apparatus of  claim 9 , wherein the distance is a first distance, the source is a first source, the acoustic signal is a first acoustic signal, the signal processing mode is a first signal processing mode, and the electrical signal is a first electric signal, the processing means to:
 estimate a second distance between a second source of a second acoustic signal and the microphone that detected the second acoustic signal;   select a second signal processing mode based on the second distance; and   process a second electrical signal representative of the second acoustic signal in accordance with the selected second signal processing mode.   
     
     
         16 . A non-transitory machine readable storage medium comprising instructions to cause at least one processor circuit to at least:
 estimate a distance between a source of an acoustic signal and a microphone that detected the acoustic signal, the estimate based on reverberation;   select a signal processing mode based on the distance; and   process an electrical signal representative of the acoustic signal in accordance with the selected signal processing mode.   
     
     
         17 . The storage medium of  claim 16 , wherein the instructions cause one or more of the at least one processor circuit to:
 identify a decibel-based metric based on the reverberation;   perform a comparison of the decibel-based metric to a threshold; and   categorize the distance as near-field or far-field based on the comparison.   
     
     
         18 . The storage medium of  claim 17 , wherein the instructions cause one or more of the at least one processor circuit to execute an artificial intelligence model to identify the decibel-based metric. 
     
     
         19 . The storage medium of  claim 18 , wherein the instructions cause one or more of the at least one processor circuit to implement a training phase in which the decibel-based metric is identified based on a direct pulse of the acoustic signal. 
     
     
         20 . The storage medium of  claim 17 , wherein the instructions cause one or more of the at least one processor circuit to dereverberate the electrical signal when the distance is far-field. 
     
     
         21 . The storage medium of  claim 16 , wherein the instructions cause one or more of the at least one processor circuit to estimate the distance for subsequent frames of the electrical signal.